© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13473
    Prev
    Next
    INDEX
    Explanations

    terms related to the Premier League and soccer statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1983
    +0.15
    0.6%
    568
    +0.14
    0.6%
    553
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.15
    0.03
    757
    +0.14
    0.03
    553
    +0.14
    0.02
    Negative Logits
     effe
    -1.15
     desir
    -1.08
     frankfurt
    -1.07
     lidl
    -1.06
     disagre
    -1.06
     reluct
    -1.05
     thut
    -1.04
     unden
    -1.03
     stockholm
    -1.03
     nece
    -1.02
    POSITIVE LOGITS
     Premier
    1.44
    Premier
    1.31
    premier
    1.15
     premier
    1.13
     Premiere
    0.94
     premiere
    0.91
     premieres
    0.76
     PREMIER
    0.72
    Premiere
    0.72
    PREMI
    0.69
    Activations Density 0.087%

    No Known Activations